SPORTSQL: An Interactive System for Real-Time Sports Reasoning and Visualization

2025-08-23

AI Summary

Dynamic sports data querying remains challenging, and non-expert users face high interaction barriers. Method: This paper introduces SPORTSQL—a modular, interactive natural language query and visualization system for the English Premier League (EPL). It builds a real-time updating Fantasy Premier League (FPL) time-series database, designs DSQABENCH—a dynamic sports question-answering benchmark comprising 1,700+ annotated SQL queries, ground-truth answers, and multi-timestamp database snapshots—and integrates large language models’ symbolic reasoning to enable end-to-end natural language → SQL → visualization generation. Contributions/Results: SPORTSQL establishes the first structured evaluation benchmark for dynamic sports data; proposes a database-aware schema linking and joint visualization generation mechanism; and supports low-latency, high-accuracy real-time querying. Experiments demonstrate significant improvements in non-expert users’ efficiency and depth of exploration for time-varying sports data.

Technology Category

Natural Language Processing: Question AnsweringData Mining & Knowledge Management: Intelligent Query ProcessingKnowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasetsSearch and Retrieval-Augmented AI: Web evaluation methodologies and metricsSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

We present a modular, interactive system, SPORTSQL, for natural language querying and visualization of dynamic sports data, with a focus on the English Premier League (EPL). The system translates user questions into executable SQL over a live, temporally indexed database constructed from real-time Fantasy Premier League (FPL) data. It supports both tabular and visual outputs, leveraging the symbolic reasoning capabilities of Large Language Models (LLMs) for query parsing, schema linking, and visualization selection. To evaluate system performance, we introduce the Dynamic Sport Question Answering benchmark (DSQABENCH), comprising 1,700+ queries annotated with SQL programs, gold answers, and database snapshots. Our demo highlights how non-expert users can seamlessly explore evolving sports statistics through a natural, conversational interface.

Problem

• Real-time sports data querying and visualization system
• Natural language to SQL translation for dynamic databases
• Interactive exploration of evolving sports statistics

Innovation

• Natural language querying with SQL translation
• Real-time sports data visualization system
• Leveraging LLMs for symbolic reasoning capabilities